From: semenzato@chromium.org
To: linux-mm@kvack.org
Cc: minchan@kernel.org, sonnyrao@chromium.org, dtor@chromium.org,
Luigi Semenzato <semenzato@chromium.org>
Subject: [PATCH 1/1] mm: smaps: split PSS into components
Date: Wed, 22 May 2019 16:53:56 -0700 [thread overview]
Message-ID: <20190522235356.153671-1-semenzato@chromium.org> (raw)
From: Luigi Semenzato <semenzato@chromium.org>
Report separate components (anon, file, and shmem)
for PSS in smaps and smaps_rollup.
This helps understand and tune the memory manager behavior
in consumer devices, particularly mobile devices. Many of
them (e.g. chromebooks and Android-based devices) use zram
for anon memory, and perform disk reads for discarded file
pages. The difference in latency is large (e.g. reading
a single page from SSD is 30 times slower than decompressing
a zram page on one popular device), thus it is useful to know
how much of the PSS is anon vs. file.
This patch also removes a small code duplication in smaps_account,
which would have gotten worse otherwise.
Signed-off-by: Luigi Semenzato <semenzato@chromium.org>
---
fs/proc/task_mmu.c | 61 ++++++++++++++++++++++++++++------------------
1 file changed, 37 insertions(+), 24 deletions(-)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 01d4eb0e6bd1..4b586c4d27b0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -417,17 +417,45 @@ struct mem_size_stats {
unsigned long shared_hugetlb;
unsigned long private_hugetlb;
u64 pss;
+ u64 pss_anon;
+ u64 pss_file;
+ u64 pss_shmem;
u64 pss_locked;
u64 swap_pss;
bool check_shmem_swap;
};
+static void smaps_page_accumulate(struct mem_size_stats *mss,
+ struct page *page, unsigned long size, unsigned long pss,
+ bool dirty, bool locked)
+{
+ mss->pss += pss;
+
+ if (PageAnon(page))
+ mss->pss_anon += pss;
+ else if (PageSwapBacked(page))
+ mss->pss_shmem += pss;
+ else
+ mss->pss_file += pss;
+
+ if (locked)
+ mss->pss_locked += pss;
+ if (dirty || PageDirty(page))
+ mss->shared_dirty += size;
+ else
+ mss->shared_clean += size;
+}
+
static void smaps_account(struct mem_size_stats *mss, struct page *page,
bool compound, bool young, bool dirty, bool locked)
{
int i, nr = compound ? 1 << compound_order(page) : 1;
unsigned long size = nr * PAGE_SIZE;
+ /*
+ * First accumulate quantities that depend only on |size| and the type
+ * of the compound page.
+ */
if (PageAnon(page)) {
mss->anonymous += size;
if (!PageSwapBacked(page) && !dirty && !PageDirty(page))
@@ -440,42 +468,24 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
mss->referenced += size;
/*
+ * Then accumulate quantities that may depend on sharing, or that may
+ * differ page-by-page.
+ *
* page_count(page) == 1 guarantees the page is mapped exactly once.
* If any subpage of the compound page mapped with PTE it would elevate
* page_count().
*/
if (page_count(page) == 1) {
- if (dirty || PageDirty(page))
- mss->private_dirty += size;
- else
- mss->private_clean += size;
- mss->pss += (u64)size << PSS_SHIFT;
- if (locked)
- mss->pss_locked += (u64)size << PSS_SHIFT;
+ smaps_page_accumulate(mss, page, size, size, dirty, locked);
return;
}
-
for (i = 0; i < nr; i++, page++) {
int mapcount = page_mapcount(page);
unsigned long pss = (PAGE_SIZE << PSS_SHIFT);
-
if (mapcount >= 2) {
- if (dirty || PageDirty(page))
- mss->shared_dirty += PAGE_SIZE;
- else
- mss->shared_clean += PAGE_SIZE;
- mss->pss += pss / mapcount;
- if (locked)
- mss->pss_locked += pss / mapcount;
- } else {
- if (dirty || PageDirty(page))
- mss->private_dirty += PAGE_SIZE;
- else
- mss->private_clean += PAGE_SIZE;
- mss->pss += pss;
- if (locked)
- mss->pss_locked += pss;
+ pss /= mapcount;
}
+ smaps_page_accumulate(mss, page, PAGE_SIZE, pss, dirty, locked);
}
}
@@ -758,6 +768,9 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss)
{
SEQ_PUT_DEC("Rss: ", mss->resident);
SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT);
+ SEQ_PUT_DEC(" kB\nPss_Anon: ", mss->pss_anon >> PSS_SHIFT);
+ SEQ_PUT_DEC(" kB\nPss_File: ", mss->pss_file >> PSS_SHIFT);
+ SEQ_PUT_DEC(" kB\nPss_Shmem: ", mss->pss_shmem >> PSS_SHIFT);
SEQ_PUT_DEC(" kB\nShared_Clean: ", mss->shared_clean);
SEQ_PUT_DEC(" kB\nShared_Dirty: ", mss->shared_dirty);
SEQ_PUT_DEC(" kB\nPrivate_Clean: ", mss->private_clean);
--
2.21.0.1020.gf2820cf01a-goog
next reply other threads:[~2019-05-22 23:54 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-22 23:53 semenzato [this message]
2019-06-26 18:04 [PATCH 1/1] mm: smaps: split PSS into components semenzato
2019-06-26 22:19 ` Andrew Morton
2019-06-26 23:40 ` Luigi Semenzato
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190522235356.153671-1-semenzato@chromium.org \
--to=semenzato@chromium.org \
--cc=dtor@chromium.org \
--cc=linux-mm@kvack.org \
--cc=minchan@kernel.org \
--cc=sonnyrao@chromium.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).